Coder's chat (chatd) can now discover and use MCP servers configured in
a workspace's `.mcp.json` file. This brings project-specific tooling
(GitHub, databases, docs servers, etc.) into the chat without any manual
configuration.
## How it works
The workspace agent reads `.mcp.json` from the workspace directory (same
format Claude Code uses), connects to the declared MCP servers —
spawning child processes for stdio servers and connecting over the
network for HTTP/SSE — and caches their tool lists. Two new agent HTTP
endpoints expose this:
- `GET /api/v0/mcp/tools` returns the cached tool list (supports
`?refresh=true`)
- `POST /api/v0/mcp/call-tool` proxies calls to the correct server
On each chat turn, chatd calls `ListMCPTools` through the existing
`AgentConn` tailnet connection, wraps each tool as a
`fantasy.AgentTool`, and adds them to the LLM's tool set alongside
built-in and admin-configured MCP tools. Tool names are prefixed with
the server name (`github__create_issue`) to avoid collisions.
Failed server connections are logged and skipped — they never block the
agent or break the chat. Child stdio processes are terminated on agent
shutdown.
*Problem:* `publishChatPubsubEvent` was constructing a partial
`codersdk.Chat` that omitted `LastModelConfigID` and other fields. Go's
zero-value UUID caused the sidebar to show "Default model" for chats
received via SSE.
*Solution:*
- Extracted `convertChat`/`convertChats` from `exp_chats.go` into
`db2sdk.Chat`/`db2sdk.Chats`, alongside existing `ChatMessage`,
`ChatQueuedMessage`, and `ChatDiffStatus` converters.
`publishChatPubsubEvent` now calls `db2sdk.Chat(chat, nil)` instead of
maintaining its own copy of the conversion logic
- Added backend integration test
`TestWatchChats/CreatedEventIncludesAllChatFields`
- Added frontend regression tests for nil-UUID and valid model config ID
cases
> 🤖 Created by Coder Agents, reviewed by this human.
Admins can now control whether the built-in Coder Agents default system
prompt is prepended to their custom instructions, rather than having the
custom prompt silently replace the default.
**Changes:**
- New `include_default_system_prompt` boolean toggle (defaults to `true`
for existing deployments) stored as a site config key — no migration
needed.
- GET `/api/experimental/chats/config/system-prompt` returns the toggle
state, the custom prompt, and a preview of the built-in default.
- PUT persists both the toggle and custom prompt atomically in a single
transaction.
- `resolvedChatSystemPrompt()` composes `[default?, custom?]` joined by
`\n\n`, falling back to the built-in default on DB errors.
- Settings UI adds a Switch toggle with conditional helper text and a
"Preview" button that shows the built-in default prompt via the existing
`TextPreviewDialog`.
- Comprehensive test coverage: 15 subtests covering toggle behavior,
prompt composition matrix, auth boundaries, and integration with chat
creation.
- Adds `GET /api/experimental/chats/by-workspace` endpoint that returns
workspace_id → latest chat_id mapping
- Modifies FE to fetch this alongside the workspace list, gated on
`agents` experiment and render an "Agent" badge similar to the existing
"Task" badge in `WorkspacesTable`
- Badge links to the "latest chat" linked to the given workspace.
Notes:
- Intentionally uses `fetchWithPostFilter` for RBAC to decouple from
workspaces API — will migrate to `workspaces_expanded` view later.
- If users have multiple chats linked to the same workspace, the badge
will link to the most recently updated one.
> 🤖 This PR was created with the help of Coder Agents, and has been
reviewed by my human. 🧑💻
## Summary
Adds an entitlement-gated **AI add-on** column to both the **Users**
table and the **Organization Members** table. When
`ai_governance_user_limit` is entitled, each row shows whether the user
is consuming an AI seat.
## Background
The AI governance add-on tracks which users are consuming AI seats.
Admins need visibility into per-user seat consumption directly from the
user management tables. This change surfaces that information through
both the site-wide Users table and the per-organization Members table,
gated behind the `ai_governance_user_limit` entitlement so the column
only appears when the feature is licensed.
## Implementation
### Backend
- **New SQL query** `GetUserAISeatStates`
(`coderd/database/queries/aiseatstate.sql`) — returns user IDs consuming
an AI seat, derived from:
- Users with entries in `aibridge_interceptions` (AI Bridge usage)
- Users who own workspaces with `has_ai_task = true` builds (AI Tasks
usage)
- **SDK types** — added `has_ai_seat: boolean` to `codersdk.User` and
`codersdk.OrganizationMemberWithUserData`
- **Handler wiring** — both the Users list endpoint (`coderd/users.go`)
and all Members endpoints (`coderd/members.go`) query AI seat state per
page of user IDs and populate the response field
- **dbauthz** — per-user `ActionRead` checks on `ResourceUserObject`
### Frontend
- **Shared `AISeatCell` component**
(`site/src/modules/users/AISeatCell.tsx`) — green `CircleCheck` for
consuming, gray `X` for non-consuming
- **`TableColumnHelpTooltip`** — extended with `ai_addon` variant with
tooltip: *"Users with access to AI features like AI Bridge, Boundary, or
Tasks who are actively consuming a seat."*
- **Column visibility** gated behind
`useFeatureVisibility().ai_governance_user_limit`
## Validation
- Backend: dbauthz full method suite (`TestMethodTestSuite`) passes
including new `GetUserAISeatStates` test
- Backend: `TestGetUsers`, `TestUsersFilter`, CLI golden file tests pass
- Frontend: 7/7 tests pass across `UsersPage.test.tsx` and
`OrganizationMembersPage.test.tsx` (column visibility gating both
directions)
- `go build ./coderd/...` compiles clean
- `pnpm --dir site run lint:types` passes
- `make gen` clean
## Risks
- **Pagination performance**: The AI seat query is scoped to the current
page's user IDs (not a full table scan), keeping it efficient for
paginated views.
- **Semantic scope**: The workspace-side AI seat derivation uses "any
build with `has_ai_task = true`" rather than "latest build only". If the
product intent is latest-build-only, this can be tightened in a
follow-up.
---
_Generated with `mux` • Model: `anthropic:claude-opus-4-6` • Thinking:
`xhigh` • Cost: `$27.25`_
<!-- mux-attribution: model=anthropic:claude-opus-4-6 thinking=xhigh
costs=27.25 -->
## Summary
This change removes the steady-state "resolve the latest workspace
agent" query from chat execution.
Instead of asking the database for the latest build's agent on every
turn, a chat now persists the workspace/build/agent binding it actually
uses and reuses that binding across subsequent turns. The common path
becomes "load the bound agent by ID and dial it", with fallback paths to
repair the binding when it is missing, stale, or intentionally changed.
## What changes
- add `workspace_id`, `build_id`, and `agent_id` binding fields to
`chats`
- expose those fields through the chat API / SDK so the execution
context is explicit
- load the persisted binding first in chatd, instead of always resolving
the latest build's agent
- persist a refreshed binding when chatd has to re-resolve the workspace
agent
- keep child / subagent chats on the same bound workspace context by
inheriting the parent binding
- leave `build_id` / `agent_id` unset for flows like `create_workspace`,
then bind them lazily on the next agent-backed turn
## Runtime behavior
The binding is treated as an optimistic cache of the agent a chat should
use:
- if the bound agent still exists and dials successfully, we use it
without a latest-build lookup
- if the bound agent is missing or no longer reachable, chatd
re-resolves against the latest build and persists the new binding
- if a workspace mutation changes the chat's target workspace, the
binding is updated as part of that mutation
To avoid reintroducing a hot-path query, dialing uses lazy validation:
- start dialing the cached agent immediately
- only validate against the latest build if the dial is still pending
after a short delay
- if validation finds a different agent, cancel the stale dial, switch
to the current agent, and persist the repaired binding
## Result
The hot path stops issuing
`GetWorkspaceAgentsInLatestBuildByWorkspaceID` for every user message,
which is the source of the DB pressure this PR is addressing. At the
same time, chats still converge to the correct workspace agent when the
binding becomes stale due to rebuilds or explicit workspace changes.
## Summary
Adds a general-purpose `map[string]string` label system to chats, stored
as jsonb with a GIN index for efficient containment queries.
This is a standalone foundational feature that will be used by the
upcoming Automations feature for session identity (matching webhook
events to existing chats), replacing the need for bespoke session-key
tables.
## Changes
### Database
- **Migration 000451**: Adds `labels jsonb NOT NULL DEFAULT '{}'` column
to `chats` table with a GIN index (`idx_chats_labels`)
- **`InsertChat`**: Accepts labels on creation via `COALESCE(@labels,
'{}')`
- **`UpdateChatByID`**: Supports partial update —
`COALESCE(sqlc.narg('labels'), labels)` preserves existing labels when
NULL is passed
- **`GetChats`**: New `has_labels` filter using PostgreSQL `@>`
containment operator
- **`GetAuthorizedChats`**: Synced with generated `GetChats` (new column
scan + query param)
### API
- **Create chat** (`POST /chats`): Accepts optional `labels` field,
validated before creation
- **Update chat** (`PATCH /chats/{chat}`): Supports `labels` field for
atomic label replacement
- **List chats** (`GET /chats`): Supports `?label=key:value` query
parameters (multiple are AND-ed)
### SDK
- `Chat`, `CreateChatRequest`, `UpdateChatRequest`, `ListChatsOptions`
all gain `Labels` fields
- `UpdateChatRequest.Labels` is a pointer (`*map[string]string`) so
`nil` means "don't change" vs empty map means "clear all"
### Validation (`coderd/httpapi/labels.go`)
- Max 50 labels per chat
- Key: 1–64 chars, must match `[a-zA-Z0-9][a-zA-Z0-9._/-]*` (supports
namespaced keys like `github.repo`, `automation/pr-number`)
- Value: 1–256 chars
- 13 test cases covering all edge cases
### Chat runtime
- `chatd.CreateOptions` gains `Labels` field, threaded through to
`InsertChat`
- Existing `UpdateChatByID` callers (e.g., quickgen title updates) are
unaffected — NULL labels preserve existing values via COALESCE
We had a bug where computer use base64-encoded screenshots would not be
interpreted as screenshots anymore once saved to the db, loaded back
into memory, and sent to Anthropic. Instead, they would be interpreted
as regular text. Once a computer use agent made enough screenshots and
stopped, and you tried sending it another message, you'd get an out of
context error:
<img width="808" height="367" alt="Screenshot 2026-03-23 at 12 02 54"
src="https://github.com/user-attachments/assets/f0bf6be2-4863-47ca-a7a9-9e6d9dfceeed"
/>
This PR fixes that.
## Summary
Introduces a new `context-file` ChatMessagePart type for persisting
workspace instruction files (AGENTS.md) as durable, frontend-visible
message parts. This is the foundation for showing loaded context files
in the chat input's context indicator tooltip.
### Problem
Previously, instruction files were resolved transiently on every turn
via `resolveInstructions()` → `InsertSystem()` and injected into the
in-memory prompt without persistence. The frontend had no knowledge that
instruction files were loaded into context, and there was no way to
surface this information to users.
### Solution
Instruction files are now read **once** when a workspace is first
attached to a chat (matching how [openai/codex handles
it](https://developers.openai.com/codex/guides/agents-md)) and persisted
as `user`-role, `both`-visibility message parts with a new
`context-file` type. This ensures:
- **Durability**: survives page refresh (data is in the DB, returned by
`getChatMessages`)
- **Cache-friendly**: `user`-role avoids the system-message hoisting
that providers do, keeping the instruction content in a stable position
for prompt caching
- **Frontend-visible**: the frontend receives paths and truncation
status for future context indicator rendering
- **Extensible**: the same pattern works for Skills (future)
### Key changes
| Layer | Change |
|---|---|
| **SDK** (`codersdk/chats.go`) | Add `ChatMessagePartTypeContextFile`
with `context_file_path`, `context_file_content` (internal, stripped
from API), `context_file_truncated` fields |
| **Prompt expansion** (`chatprompt`) | Expand `context-file` parts to
`<workspace-context>` text blocks in `partsToMessageParts()` |
| **Chat engine** (`chatd.go`) | Add `persistInstructionFiles()`, called
on first turn with a workspace. Remove per-turn `resolveInstructions()`
+ `InsertSystem()` from `processChat()` and `ReloadMessages` |
| **Frontend** | Ignore `context-file` parts in `messageParsing.ts` and
`streamState.ts` (no rendering yet — follow-up will add tooltip display)
|
### How it works
1. On each turn, `processChat` checks if any loaded message contains
`context-file` parts
2. If not (first turn with a workspace), reads AGENTS.md files via the
workspace agent connection and persists them
3. For this first turn, also injects the instruction text into the
prompt (since messages were loaded before persistence)
4. On all subsequent turns, `ConvertMessagesWithFiles()` encounters the
persisted `context-file` parts and expands them into text automatically
— no extra resolution needed
- Stores a deployment-wide agents template allowlist in `site_configs`
(`agents_template_allowlist`)
- Adds `GET/PUT /api/experimental/chats/config/template-allowlist`
endpoints
- Filters `list_templates`, `read_template`, and `create_workspace` chat
tools by allowlist, if defined (empty=all allowed)
- Add "Templates" admin settings tab in Agents UI ([what it looks
like](https://624de63c6aacee003aa84340-sitjilsyrr.chromatic.com/?path=/story/pages-agentspage-agentsettingspageview--template-allowlist))
> 🤖 This PR was created with the help of Coder Agents, and has been
reviewed by my human. 🧑💻
> **PR Stack**
> 1. #23351 ← `#23282`
> 2. #23282 ← `#23275`
> 3. **#23275** ← `#23349` *(you are here)*
> 4. #23349 ← `main`
---
## Summary
Extracts a structured error classification subsystem for agent chat
(`chatd`) so that retry and error payloads carry machine-readable
metadata — error kind, provider name, HTTP status code, and retryability
— instead of raw error strings.
This is the **backend half** of the error-handling work. The frontend
counterpart is in #23282.
## Changes
### New package: `coderd/chatd/chaterror/`
Canonical error classification — extracts error kind, provider, status
code, and user-facing message from raw provider errors. One source of
truth that drives both retry policy and stream payloads.
- **`kind.go`**: Error kind enum (`rate_limit`, `timeout`, `auth`,
`config`, `overloaded`, `unknown`).
- **`signals.go`**: Signal extraction — parses provider name, HTTP
status code, and retryability from error strings and wrapped types.
- **`classify.go`**: Classification logic — maps extracted signals to an
error kind.
- **`message.go`**: User-facing message templates keyed by kind +
signals.
- **`payload.go`**: Projectors that build `ChatStreamError` and
`ChatStreamRetry` payloads from a classified error.
### Modified
- **`codersdk/chats.go`**: Added `Kind`, `Provider`, `Retryable`,
`StatusCode` fields to `ChatStreamError` and `ChatStreamRetry`.
- **`coderd/chatd/chatretry/`**: Thinned to retry-policy only;
classification logic moved to `chaterror`.
- **`coderd/chatd/chatloop/`**: Added per-attempt first-chunk timeout
(60 s) via `guardedStream` wrapper — produces retryable
`startup_timeout` errors instead of hanging forever.
- **`coderd/chatd/chatd.go`**: Publishes normalized retry/error payloads
via `chaterror` projectors.
<!--
If you have used AI to produce some or all of this PR, please ensure you have read our [AI Contribution guidelines](https://coder.com/docs/about/contributing/AI_CONTRIBUTING) before submitting.
-->
_Disclaimer:_ _initially_ _produced_ _by_ _Claude_ _Opus_ _4\.6,_ _heavily_ _modified_ _and_ _reviewed_ _by_ _me._
Closes https://github.com/coder/internal/issues/1360
Adds a new `/api/v2/aibridge/sessions` API which returns "sessions".
Sessions, as defined in the [RFC](https://www.notion.so/coderhq/AI-Bridge-Sessions-Threads-2ccd579be59280f28021d3baf7472fbe?source=copy_link), are a set of interceptions logically grouped by a session key issued by the client.
The API design for this endpoint was done in [this doc](https://github.com/coder/internal/issues/1360).
If the client has not provided a session ID, we will revert to the thread root ID, and if that's not present we use the interception's own ID (i.e. a session of a single interception - which is effectively what we show currently in our `/api/v2/aibridge/interceptions` API).
The SQL query looks gnarly but it's relatively simple, and seems to perform well (~200ms) even when I import dogfood's `aibridge_*` tables into my workspace. If we need to improve performance on this later we can investigate materialized views, perhaps, but for now I don't think it's warranted.
---
_The PR looks large but it's got a lot of generated code; the actual changes aren't huge._
## What
Adds per-user per-model auto-compaction threshold overrides. Users can
now customize the percentage of context window usage that triggers chat
compaction, independently for each enabled model.
## Why
The compaction threshold was previously only configurable at the
deployment level (`chat_model_configs.compression_threshold`). Different
users have different preferences — some want aggressive compaction to
keep costs low, others prefer higher thresholds to retain more context.
This gives users control without requiring admin intervention.
## Architecture
**Storage:** Reuses the existing `user_configs` table (no migration
needed). Overrides are stored as key/value pairs with keys shaped
`chat_compaction_threshold:<modelConfigID>` and integer percent values.
**API:** Three new experimental endpoints under
`/api/experimental/chats/config/`:
- `GET /user-compaction-thresholds` — list all overrides for the current
user
- `PUT /user-compaction-thresholds/{modelConfig}` — upsert an override
(validates model exists and is enabled, validates 0–100 range)
- `DELETE /user-compaction-thresholds/{modelConfig}` — clear an override
(idempotent)
**Runtime resolution:** In `coderd/chatd/chatd.go`, a new
`resolveUserCompactionThreshold()` helper runs at the start of each chat
turn (inside `runChat()`), after the model config is resolved but before
`CompactionOptions` is built. If a valid override exists, it replaces
`modelConfig.CompressionThreshold`. The threshold source
(`user_override` vs `model_default`) is logged with each compaction
event.
**Precedence:** `effectiveThreshold = userOverride ??
modelConfig.CompressionThreshold`
**UI:** New "Context Compaction" subsection in the Agents → Settings →
Behavior tab, placed after Personal Instructions. Shows one row per
enabled model with the system default, a number input for the override,
and Save/Reset controls.
## Testing
- 9 API subtests covering CRUD, validation (boundary values 0/100,
out-of-range rejection), upsert behavior, idempotent delete, user
isolation, and non-existent model config
- 4 dbauthz tests (16 scenarios) verifying `ActionReadPersonal` /
`ActionUpdatePersonal` on all query methods
- 4 Storybook stories with play functions (Default, WithOverrides,
Loading, Error)
<details>
<summary>Implementation plan</summary>
### Phase 1 — Tests
- Backend API tests in `coderd/chats_test.go` (9 subtests)
- Database auth wrapper tests in
`coderd/database/dbauthz/dbauthz_test.go` (4 methods)
- Frontend stories in `UserCompactionThresholdSettings.stories.tsx` (4
stories)
### Phase 2 — Backend preference surface
- 4 SQL queries in `coderd/database/queries/users.sql` (list, get,
upsert, delete)
- `make gen` to propagate into generated artifacts
- Auth/metrics wrappers in dbauthz and dbmetrics
- SDK types and client methods in `codersdk/chats.go`
- HTTP handlers and routes in `coderd/chats.go` and `coderd/coderd.go`
- Key prefix constant shared between handlers and runtime
### Phase 3 — Runtime override
- `resolveUserCompactionThreshold()` helper in `coderd/chatd/chatd.go`
- Override injection in `runChat()` before building `CompactionOptions`
- `threshold_source` field added to compaction log
### Phase 4 — Settings UI
- API client methods and React Query hooks in `site/src/api/`
- `UserCompactionThresholdSettings` component extracted from
`SettingsPageContent`
- Per-model mutation tracking (only the active row disables during save)
- 100% warning, "System default" label, helpful empty state copy
### Phase 5 — Refactor and review fixes
- Consolidated key prefix constant in `codersdk`
- Explicit PUT range validation (not just struct tags)
- GET handler gracefully skips malformed rows instead of 500
- Boundary value, upsert, and non-existent model config tests
- UX improvements: per-model mutation state, aria-live on errors
</details>
- Changes all 41 chat method receivers in `codersdk/chats.go` from
`*Client` to `*ExperimentalClient` to ensure that callers are aware that
these reference potentially unstable `/api/experimental` endpoints.
> 🤖 This PR was created with the help of Coder Agents, and has been
reviewed by my human. 🧑💻
This PR changes agents desktop resolution from 1366x768 to 1920x1080.
Anthropic requires the that the resolution of desktop screenshots fits
in 1,150,000 total pixels, so we downscale screenshots to 1280x720
before sending them to the LLM provider.
Resolution scaling was already implemented, but our code didn't exercise
it. The resolution bump showed that there were some bugs in the scaling
logic - this PR fixes these bugs too.
Continuation of https://github.com/coder/coder/pull/23067
Add filtering to the paginated org member endpoint (pretty much the same
as what I did in the previous PR with group members, except there I also
had to add pagination since it was missing).
Partially addresses #21813 (still need to make changes to the "add user"
button to be complete)
Since there are a lot of user tests already, I moved them into
`coderdtest` to be shared.
- Add `agents_workspace_ttl` site config (default: whatever the template
says a.k.a. `0s`)
- Expose via GET/PUT `/api/experimental/chats/config/workspace-ttl`
- Chat tool reads setting and passes `TTLMillis` on workspace creation
- Existing autostop infrastructure handles the rest (zero changes to
LifecycleExecutor, CalculateAutostop, or activity bumping)
- ⚠️ Template-level `UserAutostopEnabled=false` overrides this global
default. Not touching this.
- Frontend: "Workspace Lifetime" control in /agents/settings Behavior
tab (admin-only)
> This PR was created with the help of Coder Agents, and has been
reviewed by several humans and robots. 🤖🤝🧑💻
Replace the 200ms polling loop in chatd's execute and
process_output tools with server-side blocking via sync.Cond
on HeadTailBuffer.
The agent's GET /{id}/output endpoint accepts ?wait=true to
block until the process exits or a 5-minute server cap expires.
The process_output tool blocks by default for 10s (overridable
via wait_timeout), and falls back to a non-blocking snapshot on
timeout. The execute tool's foreground path makes a single
blocking call instead of polling.
Related #23316
## Description
Blocks `CONNECT` tunnels to private and reserved IP ranges in
aibridgeproxyd, preventing the proxy from being used to reach internal
networks.
The Coder access URL is always exempt (hostname+port match) so the proxy
can reach its own deployment. It is possible to exempt additional ranges
via `CODER_AIBRIDGE_PROXY_ALLOWED_PRIVATE_CIDRS`.
DNS rebinding is handled differently per path:
* Direct (no upstream proxy): validate the resolved IP right before the
TCP dial, no window between check and connect.
* Upstream proxy: Resolves and checks before forwarding to the upstream
dialer. A small rebinding window exists since the upstream proxy
re-resolves independently.
## Changes
* Add blocked IP denylist covering private, reserved, and
special-purpose ranges
* Add `AllowedPrivateCIDRs` option with CLI flag and env var
* Wire IP checks into `proxy.ConnectDial` for both upstream and direct
paths
* Add tests for blocked/allowed cases across direct dial, upstream
proxy, CIDR exemptions, and CoderAccessURL exemption
Notes: documentation will be handled in a follow-up PR.
Closes: https://github.com/coder/security/issues/124
## Summary
Adds the database schema, API endpoints, SDK types, and encryption
wrappers for admin-managed MCP (Model Context Protocol) server
configurations that chatd can consume. This is the backend foundation
for allowing external MCP tools (Sentry, Linear, GitHub, etc.) to be
used during AI chat sessions.
## Database
Two new tables:
- **`mcp_server_configs`**: Admin-managed server definitions with URL,
transport (Streamable HTTP / SSE), auth config (none / OAuth2 / API key
/ custom headers), tool allow/deny lists, and an availability policy
(`force_on` / `default_on` / `default_off`). Includes CHECK constraints
on transport, auth_type, and availability values.
- **`mcp_server_user_tokens`**: Per-user OAuth2 tokens for servers
requiring individual authentication. Cascades on user/config deletion.
New column on `chats` table:
- **`mcp_server_ids UUID[]`**: Per-chat MCP server selection, following
the same pattern as `model_config_id` — passed at chat creation,
changeable per-message with nil-means-no-change semantics.
## API Endpoints
All routes are under `/api/experimental/mcp/servers/` and gated behind
the `agents` experiment.
**Admin endpoints** (`ResourceDeploymentConfig` auth):
- `POST /` — Create MCP server config
- `PATCH /{id}` — Update MCP server config (full-replace)
- `DELETE /{id}` — Delete MCP server config
**Authenticated endpoints** (all users, enabled servers only for
non-admins):
- `GET /` — List configs (admins see all, members see enabled-only with
admin fields redacted)
- `GET /{id}` — Get config by ID (with `auth_connected` populated
per-user)
**OAuth2 per-user auth flow:**
- `GET /{id}/oauth2/connect` — Initiate OAuth2 flow (state cookie CSRF
protection)
- `GET /{id}/oauth2/callback` — Handle OAuth2 callback, store tokens
- `DELETE /{id}/oauth2/disconnect` — Remove stored OAuth2 tokens
## Security
- **Secrets never returned**: `OAuth2ClientSecret`, `APIKeyValue`, and
`CustomHeaders` are never in API responses — only boolean indicators
(`has_oauth2_secret`, `has_api_key`, `has_custom_headers`).
- **Field redaction for non-admins**: `convertMCPServerConfigRedacted`
strips `OAuth2ClientID`, auth URLs, scopes, and `APIKeyHeader` from
non-admin responses.
- **dbcrypt encryption at rest**: All 5 secret fields use `dbcrypt_keys`
encryption with full encrypt-on-write / decrypt-on-read wrappers (11
dbcrypt method overrides + 2 helpers), following the same pattern as
`chat_providers.api_key`.
- **OAuth2 CSRF protection**: State parameter stored in `HttpOnly`
cookie with `HTTPCookies.Apply()` for correct `Secure`/`SameSite` behind
TLS-terminating proxies.
- **dbauthz authorization**: All 18 querier methods have authorization
wrappers. Read operations use `ActionRead`, write operations use
`ActionUpdate` on `ResourceDeploymentConfig`.
## Governance Model
| Control | Implementation |
|---------|---------------|
| **Global kill switch** | `enabled` defaults to `false` |
| **Availability policy** | `force_on` (always injected), `default_on`
(pre-selected), `default_off` (opt-in) |
| **Per-chat selection** | `mcp_server_ids` on `CreateChatRequest` /
`CreateChatMessageRequest` |
| **Auth gate** | OAuth2 servers require per-user auth before tools are
injected |
| **Tool-level allow/deny** | Arrays on `mcp_server_configs` for
granular tool filtering |
| **Secrets encrypted at rest** | Uses `dbcrypt_keys` (same pattern as
`chat_providers.api_key`) |
## Tests
8 test functions covering:
- Full CRUD lifecycle (create, list, update, delete)
- Non-admin visibility filtering (enabled-only, field redaction)
- `auth_connected` population for OAuth2 vs non-OAuth2 servers
- Availability policy validation (valid values + invalid rejection)
- Unique slug enforcement (409 Conflict)
- OAuth2 disconnect idempotency
- Chat creation with `mcp_server_ids` persistence
## Known Limitations (Deferred)
These are documented and intentional for an experimental feature:
- **Audit logging** not yet wired — will add when feature stabilizes
- **Cross-field validation** (e.g., OAuth2 fields required when
`auth_type=oauth2`) — admin-only endpoint, will add when stabilizing
- **`force_on` auto-injection** — query exists but not yet wired into
chatd tool injection (follow-up)
- **Additional test coverage** — 403 auth tests, GET-by-ID tests,
callback CSRF tests planned for follow-up
## What's NOT in this PR
- Frontend UI (admin panel + chat picker)
- Actual MCP client connections (`chatd/chatmcp/` manager)
- Tool injection into `chatloop/`
Updates the `charm.land/fantasy` replace to the rebased `cj/go1.25`
branch on `kylecarbs/fantasy`, which now includes:
- **chore: downgrade to Go 1.25**
- **feat: anthropic computer use**
- **chore: use kylecarbs/openai-go fork for coder/coder compat**
Switches the `openai-go/v3` replace from `SasSwart/openai-go` →
`kylecarbs/openai-go`, which is the same SasSwart perf fork plus a fix
for `WithJSONSet` being clobbered by deferred body serialization.
Without the fix, `NewStreaming` silently drops `stream: true` from
requests. See https://github.com/kylecarbs/openai-go/pull/2 for details.
- Adds a new API endpoint `GET /api/v2/users/oidc-claims` that returns
only the **merged claims** (not the separate id_token/userinfo
breakdown). Scoped exclusively to the authenticated user's own identity
— no user parameter, so users cannot view each other's claims.
- Adds a new CLI command:** `coder users oidc-claims` that hits the
above endpoint.
- The existing owner-only debug endpoint is preserved unchanged for
admins who need the full claim breakdown.
> 🤖 This PR was created with the help of Coder Agents, and will be
reviewed by my human. 🧑💻
ChatMessagePart uses a flat struct with omitempty on all fields,
but some fields are required in their TypeScript variant (no ?
suffix in the variants struct tag). When Go omits a zero-valued
required field, the frontend receives undefined where it expects
a concrete value.
Remove omitempty from fields that are required in at least one
variant: Text, URL, MediaType, FileName, StartLine, EndLine,
Content. Fields where all variants use ? keep omitempty.
Add a sub-test to TestChatMessagePartVariantTags that enforces
this invariant via reflection so future additions cannot
reintroduce the mismatch.
Supersedes #23249
Go serializes ChatMessagePart.Text with omitempty, so empty
reasoning text (from reasoning_start with no delta) is omitted
from JSON. The frontend receives {type: "reasoning"} with text
as undefined, crashing on .trim() calls.
Mark Text as optional in the reasoning variant via the variants
struct tag. This generates ChatReasoningPart with text?: string
and the frontend falls back to "" via nullish coalescing.
Closes#23245
## What
Adds a new admin-only **PR Insights** page for the `/agents` analytics
view — a dashboard for engineering leaders to understand code shipped by
AI agents.
### Backend
- `GET /api/v2/chats/insights/pull-requests` — admin-only endpoint
- 4 SQL queries in `chatinsights.sql` aggregating `chat_diff_statuses`
joined with chat cost data (via root chat tree rollup)
- Runs 5 parallel DB queries: current summary, previous summary (for
trends), time series, per-model breakdown, recent PRs
- SDK types auto-generate to TypeScript
### Frontend (`PRInsightsView`)
- **Stat cards**: PRs created, Merged, Merge rate, Lines shipped,
Cost/merged PR — with trend badges comparing to previous period
- **Activity chart**: Stacked area chart (created/merged/closed) using
git color tokens (`git-added-bright`, `git-merged-bright`,
`git-deleted-bright`)
- **Model performance table**: Per-model PR counts, inline merge rate
bars, diff stats, cost breakdown
- **Recent PRs table**: Status badges, review state icons, author info,
external links
- **Time range filter**: 7d/14d/30d/90d button group
- **4 Storybook stories**: Default, HighPerformance, LowVolume, NoPRs
### Data source
All PR data comes from the existing `chat_diff_statuses` table
(populated by the `gitsync.Worker` background job that polls GitHub
every 120s). No new data collection required.
### Screenshot
View in Storybook: `pages/AgentsPage/PRInsightsView`
## Summary
- add a hidden deployment config option for chat acquire batch size
(`CODER_CHAT_ACQUIRE_BATCH_SIZE` / `chat.acquireBatchSize`)
- thread the configured value into chatd startup while preserving the
existing default of `10`
- clamp the deployment value to the `int32` range before passing it into
chatd
- regenerate the API/docs/types/testdata artifacts for the new config
field
## Why
`chatd` currently acquires pending chats in batches of `10` via a
compile-time default. This change makes that batch size
operator-configurable from deployment config, so we can tune acquisition
behavior without another code change.
Both message parsers accepted untyped input and relied on scattered
asRecord/asString calls to extract fields at runtime. With the
discriminated ChatMessagePart union, both accept typed input directly
and narrow via switch (part.type).
parseMessageContent narrows from (content: unknown) to
(content: readonly ChatMessagePart[] | undefined), removing legacy
input shape handling the Go backend normalizes away.
applyMessagePartToStreamState narrows from Record<string, unknown>
to ChatMessagePart.
The SSE type guards had a & Record<string, unknown> intersection
that widened everything untyped downstream. Since the data comes
from our own API, the intersection was removed and all handlers in
ChatContext now use generated types directly.
Fixes tool_call_id and tool_name variant tags in codersdk/chats.go:
marked optional to match reality (Go guards against empty values,
omitempty omits them at the wire level).
Refs #23168, #23175
## Summary
- add shared MCP annotation metadata to toolsdk tools
- emit MCP tool annotations from both coderd and CLI MCP servers
- cover annotation serialization in toolsdk, coderd MCP e2e, and CLI MCP
tests
## Why
- Coder already exposed MCP tools, but it did not populate MCP tool
annotation hints (`readOnlyHint`, `destructiveHint`, `idempotentHint`,
`openWorldHint`).
- Hosts such as Claude Desktop use those hints to classify and group
tools, so without them Coder tools can get lumped together.
- This change adds a shared annotation source in `toolsdk` and has both
MCP servers emit those hints through `mcp.Tool.Annotations`, avoiding
drift between local and remote MCP implementations.
## Testing
- Tested locally on Cladue Desktop and the tools are categorized
correctly.
<table>
<tr>
<td> Before
<td> After
<tr>
<td> <img width="613" height="183" alt="image"
src="https://github.com/user-attachments/assets/29d2e3fb-53bc-4ea7-bdb3-f10df4ef996b"
/>
<td> <img width="600" height="457" alt="image"
src="https://github.com/user-attachments/assets/cc384036-c9a7-4db9-9400-43ad51920ff5"
/>
</table>
Note: Done using Coder Agents, reviewed and tested by human locally
The flat ChatMessagePart interface had 20+ optional fields, preventing
TypeScript from narrowing types on switch(part.type). Each consumer
needed runtime validation, type assertions, or defensive ?. chains.
Add `variants` struct tags to ChatMessagePart fields declaring which
union variants include each field. A codegen mutation in apitypings
reads these tags via reflect and generates per-variant sub-interfaces
(ChatTextPart, ChatReasoningPart, etc.) plus a union type alias.
A test validates every field has a variants tag or is explicitly
excluded, and every part type is covered.
Remove dead frontend code: normalizeBlockType, alias case branches
("thinking", "toolcall", "toolresult"), legacy field fallbacks
(line_number, typedBlock.name/id/input/output), and result_delta
handling. Add test coverage for args_delta streaming, provider_executed
skip logic, and source part parsing.
Adds a new `site_config` entry that controls whether the virtual desktop
feature for Coder Agents is enabled. It can be set via a new
`/api/experimental/chats/config/desktop-enabled` endpoint, which will be
used by the frontend.
## Summary
Remove the `hidden` tag from the `PromptCacheKey` field on
`ChatModelOpenAIProviderOptions` so the auto-generated JSON schema
no longer marks it as hidden. This allows the admin model
configuration UI to render a "Prompt Cache Key" text input for
OpenAI models alongside other visible options like Reasoning Effort,
Service Tier, and Web Search.
## Changes
- **`codersdk/chats.go`**: Remove `hidden:"true"` from `PromptCacheKey`
struct tag.
- **`site/src/api/chatModelOptionsGenerated.json`**: Regenerated via
`make gen` — `hidden: true` removed from the `prompt_cache_key` entry.
- **`modelConfigFormLogic.test.ts`**: Extend existing "all fields set"
tests to cover extract and build roundtrip for `promptCacheKey`.
## How it works
The `hidden` Go struct tag propagates through the code generation
pipeline:
1. Go struct tag → `scripts/modeloptionsgen` →
`chatModelOptionsGenerated.json`
2. The frontend `getVisibleProviderFields()` filters out fields with
`hidden: true`
3. Removing the tag makes the field visible in the schema-driven form
renderer
No new UI components are needed — the existing `ModelConfigFields`
component
automatically renders the field as a text input based on the schema
(`type: "string"`, `input_type: "input"`).
The field appears as **"Prompt Cache Key"** with description
"Key for enabling cross-request prompt caching" in the OpenAI provider
section of the admin model configuration form.
Introduce a three-way workspace sharing setting (none, everyone,
service_accounts) replacing the boolean workspace_sharing_disabled.
In service_accounts mode, only service account-owned workspaces can be
shared while regular members' share permissions are removed. Adds a
new organization-service-account system role with per-org permissions
reconciled alongside the existing organization-member system role.
Related to:
https://linear.app/codercom/issue/PLAT-28/feat-service-accounts-sharing-mode-and-rbac-role
---------
Co-authored-by: Steven Masley <Emyrk@users.noreply.github.com>
Co-authored-by: Kayla はな <mckayla@hey.com>
Adds cursor-based pagination to the chat messages endpoint.
## Backend
- New `GetChatMessagesByChatIDPaginated` SQL query: returns messages in
`id DESC` order with a `before_id` keyset cursor and configurable
`limit`
- Handler parses `?before_id=N&limit=N` query params, uses the `LIMIT
N+1` trick to set `has_more` without a separate COUNT query
- Queued messages only returned on the first page (no cursor) since
they're always the most recent
- SDK client updated with `ChatMessagesPaginationOptions`
- Fully backward compatible: omitting params returns the 50 newest
messages
## Frontend
- Switches `getChatMessages` from `useQuery` to `useInfiniteQuery` with
cursor chaining via `getNextPageParam`
- Pages flattened and sorted by `id` ascending for chronological display
- `MessagesPaginationSentinel` component uses `IntersectionObserver`
(200px rootMargin prefetch) inside the existing `flex-col-reverse`
scroll container
- `flex-col-reverse` handles scroll anchoring natively when older
messages are prepended — no manual `scrollTop` adjustment needed (same
pattern as coder/blink)
## Why cursor-based instead of offset/limit
Offset-based pagination breaks when new messages arrive while paginating
backward (offsets shift, causing duplicates or missed messages). The
`before_id` cursor is stable regardless of inserts — each page is
deterministic.
## Problem
The `edit_files` tool used `strings.ReplaceAll` for exact substring
matches, silently replacing **every** occurrence. When an LLM's search
string wasn't unique in the file, this caused unintended edits. Fuzzy
matches (passes 2 and 3) only replaced the first occurrence, creating
inconsistent behavior. Zero matches were also silently ignored.
## Investigation
Investigated how **coder/mux** and **openai/codex** handle this:
| Tool | Multiple matches | No match | Flag |
|---|---|---|---|
| **coder/mux** `file_edit_replace_string` | Error (default
`replace_count=1`) | Error | `replace_count` (int, default 1, -1=all) |
| **openai/codex** `apply_patch` | Uses first match after cursor
(structural disambiguation via context lines + `@@` markers) | Error |
None (different paradigm) |
| **coder/coder** `edit_files` (before) | Exact: replaces all. Fuzzy:
replaces first. | Silent success | None |
## Solution
Adopted the mux approach (error on ambiguity) with a simpler
`replace_all: bool` instead of `replace_count: int`:
- **Default (`replace_all: false`)**: search string must match exactly
once. Multiple matches → error with guidance: *"search string matches N
occurrences. Include more surrounding context to make the match unique,
or set replace_all to true"*
- **`replace_all: true`**: replaces all occurrences (opt-in for
intentional bulk operations like variable renames)
- **Zero matches**: now returns an error instead of silently succeeding
Chose `bool` over `int` count because:
1. LLMs are bad at counting occurrences
2. The real intent is binary (one specific spot vs. all occurrences)
3. Simpler error recovery loop for the LLM
## Changes
| File | Change |
|---|---|
| `codersdk/workspacesdk/agentconn.go` | Add `ReplaceAll bool` to
`FileEdit` struct |
| `agent/agentfiles/files.go` | Count matches before replacing; error if
>1 and not opted in; error on zero matches; add `countLineMatches`
helper |
| `codersdk/toolsdk/toolsdk.go` | Expose `replace_all` in tool schema
with description |
| `agent/agentfiles/files_test.go` | Update existing tests, add
`EditEditAmbiguous`, `EditEditReplaceAll`, `NoMatchErrors`,
`AmbiguousExactMatch`, `ReplaceAllExact` |
The `/chats/{chat}/diff-status` endpoint was redundant because:
- The `Chat` type already has a `DiffStatus` field
- Listing chats already resolves and returns `diff_status`
- The `getChat` endpoint was the only one not resolving it (passing
`nil`)
## Changes
**Backend:**
- `getChat` now calls `resolveChatDiffStatus` and includes the result in
the response
- Removed `getChatDiffStatus` handler, route (`GET /diff-status`), and
SDK method
- Tests updated to use `GetChat` instead of `GetChatDiffStatus`
**Frontend:**
- `AgentDetail.tsx`: uses `chatQuery.data?.diff_status` instead of
separate query
- `RemoteDiffPanel.tsx`: accepts `diffStatus` as a prop instead of
fetching internally
- `AgentsPage.tsx`: `diff_status_change` events now invalidate the chat
query
- Removed `chatDiffStatus` query, `chatDiffStatusKey`, and
`getChatDiffStatus` API method
Adds the `head_branch` field (the source/feature branch name of a PR) to
the diff status pipeline. Previously only `base_branch` (target branch)
and the head commit SHA were captured from the GitHub API, but not the
head branch name itself.
## Changes
- **Migration 438**: Add `head_branch` nullable TEXT column to
`chat_diff_statuses`
- **gitprovider**: Parse `head.ref` from the GitHub API response
(alongside `head.sha`) and add `HeadBranch` to `PRStatus`
- **gitsync**: Wire `HeadBranch` through `refreshOne()` into the DB
upsert params
- **worker**: Map `HeadBranch` in `chatDiffStatusFromRow()`
- **coderd**: Convert `HeadBranch` in `convertChatDiffStatus()`
- **codersdk**: Expose as `head_branch` (`*string`, omitempty) in
`ChatDiffStatus` API response
- **Tests**: Updated `github_test.go` pull JSON fixtures and assertions
Surfaces cache token data in the analytics views and fixes table
spacing.
### Changes
- **Cache token columns**: Added cache read and cache write token counts
to all analytics views (user and admin), from SQL queries through Go SDK
types to the frontend tables and summary cards.
- **Table spacing fix**: Replaced the bare React fragment in
`ChatCostSummaryView` with a `space-y-6` container so the model and chat
breakdown tables no longer overlap.
### Data flow
`chat_messages` table already stores `cache_read_tokens` and
`cache_creation_tokens` (and uses them for cost calculation). This PR
aggregates and displays them alongside input/output tokens in:
- Summary cards (6 cards: Total Cost, Input, Output, Cache Read, Cache
Write, Messages)
- Per-model breakdown table
- Per-chat breakdown table
- Admin per-user table
This PR adds a `WatchAllWorkspaces` function with `watch-all-workspaces`
endpoint, which can be used to listen on a single global pubsub channel
for _all_ workspace build updates, and makes use of it in the autostart
scaletest.
This negates the need to use a workspace watch pubsub channel _per_
workspace, which has auth overhead associated with each call. This is
especially relevant in situations such as the autostart scaletest, where
we need to start/stop a set of workspaces before we can configure their
autostart config. The overhead associated with all the watch requests
skews the scaletest results and makes it harder to reason about the
performance of the autostart feature itself.
The autostart scaletest also no longer generates its own metrics nor
does it wait for all the workspaces to actually start via autostart. We
should update the scaletest dashboard after both PRs are merged to
measure autostart performance via the new metrics.
The new function/endpoint and its usage in the autostart scaletest are
gated behind an experiment feature flag, this is something we should
discuss whether we want to enable the endpoint in prod by default or
not. If so, we can remove the experiment.
---------
Signed-off-by: Callum Styan <callumstyan@gmail.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Co-authored-by: Callum Styan <callum@coder.com>
Kyle Carberry